© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77842
    Prev
    Next
    INDEX
    Explanations

    French institutions and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.28
    などを
    -1.15
    を
    -1.14
     We
    -1.05
    ですので
    -1.01
     by
    -1.00
     since
    -0.98
     just
    -0.93
     Nearly
    -0.92
     with
    -0.88
    POSITIVE LOGITS
     этом
    1.22
     abord
    1.21
     hermosas
    1.18
     alteration
    1.18
     извест
    1.16
     ous
    1.16
     empuj
    1.15
     oscuro
    1.14
     amazing
    1.13
     afront
    1.12
    Activations Density 0.003%

    No Known Activations